{"object":"list","data":[{"id":"amazon/amazon.titan-embed-image-v1","object":"model","created":1793044729,"owned_by":"amazon","model_name":"amazon.titan-embed-image-v1","context_length":128,"max_input_tokens":128,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Amazon Titan Multimodal Embeddings G1 embeds text, images, or text and image together into a shared vector space for multimodal search and recommendation.","source":"https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/providers?model=amazon.titan-image-generator-v1","capabilities":{"input_modalities":["text","image"],"output_modalities":["text","embeddings"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":true,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_image":0.00006,"input_cost_per_token":8e-7,"output_cost_per_token":0.0,"input_cost_per_image_token":0.00006},"list_pricing":{"input_cost_per_image":0.00006,"input_cost_per_token":8e-7,"output_cost_per_token":0.0,"input_cost_per_image_token":0.00006},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/amazon.titan-embed-image-v1@us","object":"model","created":1793044729,"owned_by":"amazon","model_name":"amazon.titan-embed-image-v1","context_length":128,"max_input_tokens":128,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Amazon Titan Multimodal Embeddings G1 embeds text, images, or text and image together into a shared vector space for multimodal search and recommendation.","source":"https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/providers?model=amazon.titan-image-generator-v1","capabilities":{"input_modalities":["text","image"],"output_modalities":["text","embeddings"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":true,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_image":0.00006,"input_cost_per_token":8e-7,"output_cost_per_token":0.0,"input_cost_per_image_token":0.00006},"list_pricing":{"input_cost_per_image":0.00006,"input_cost_per_token":8e-7,"output_cost_per_token":0.0,"input_cost_per_image_token":0.00006},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/amazon.titan-embed-text-v1","object":"model","created":1793044727,"owned_by":"amazon","model_name":"amazon.titan-embed-text-v1","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Amazon Titan Embeddings G1 - Text is the first-generation Titan text embedding model.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/amazon.titan-embed-text-v2:0","object":"model","created":1793044722,"owned_by":"amazon","model_name":"amazon.titan-embed-text-v2:0","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Amazon Titan Text Embeddings V2 is a text embedding model for retrieval, search, and clustering.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/amazon.titan-embed-text-v2:0@us","object":"model","created":1793044722,"owned_by":"amazon","model_name":"amazon.titan-embed-text-v2:0","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Amazon Titan Text Embeddings V2 is a text embedding model for retrieval, search, and clustering.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"infomaniak/mini_lm_l12_v2","object":"model","created":1792525588,"owned_by":"infomaniak","model_name":"mini_lm_l12_v2","context_length":128,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ch","name":"Switzerland"}],"zero_data_retention":true,"alias_of":null},{"id":"infomaniak/bge_multilingual_gemma2","object":"model","created":1792029544,"owned_by":"infomaniak","model_name":"bge_multilingual_gemma2","context_length":8000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.12920197906647e-8},"list_pricing":{"input_cost_per_token":7.12920197906647e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ch","name":"Switzerland"}],"zero_data_retention":true,"alias_of":null},{"id":"infomaniak/Qwen/Qwen3-Embedding-8B","object":"model","created":1792029544,"owned_by":"infomaniak","model_name":"Qwen/Qwen3-Embedding-8B","context_length":8192,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":"Qwen/Qwen3-Embedding-8B","open_weights":true,"knowledge_cutoff":null,"reasoning":null,"description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.677602131302352e-8},"list_pricing":{"input_cost_per_token":7.677602131302352e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ch","name":"Switzerland"}],"zero_data_retention":true,"alias_of":null},{"id":"ionos/BAAI/bge-m3","object":"model","created":1792029544,"owned_by":"ionos","model_name":"BAAI/bge-m3","context_length":8192,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":"BAAI/bge-m3","open_weights":true,"knowledge_cutoff":null,"reasoning":null,"description":"The bge-m3 embedding model encodes sentences, paragraphs, and long documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for multilingual retrieval, semantic search, and large-context applications.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.193600608943529e-8},"list_pricing":{"input_cost_per_token":2.193600608943529e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ionos/Qwen/Qwen3-VL-Embedding-8B","object":"model","created":1792029544,"owned_by":"ionos","model_name":"Qwen/Qwen3-VL-Embedding-8B","context_length":32768,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0968003044717645e-7},"list_pricing":{"input_cost_per_token":1.0968003044717645e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ionos/sentence-transformers/paraphrase-multilingual-mpnet-base-v2","object":"model","created":1792029544,"owned_by":"ionos","model_name":"sentence-transformers/paraphrase-multilingual-mpnet-base-v2","context_length":128,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0968003044717646e-8},"list_pricing":{"input_cost_per_token":1.0968003044717646e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ovhcloud/bge-m3","object":"model","created":1792029544,"owned_by":"ovhcloud","model_name":"bge-m3","context_length":8192,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":"BAAI/bge-m3","open_weights":true,"knowledge_cutoff":null,"reasoning":null,"description":"The bge-m3 embedding model encodes sentences, paragraphs, and long documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for multilingual retrieval, semantic search, and large-context applications.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-8},"list_pricing":{"input_cost_per_token":1e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ovhcloud/bge-multilingual-gemma2","object":"model","created":1792029544,"owned_by":"ovhcloud","model_name":"bge-multilingual-gemma2","context_length":8192,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-8},"list_pricing":{"input_cost_per_token":1e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ovhcloud/Qwen3-Embedding-8B","object":"model","created":1792029544,"owned_by":"ovhcloud","model_name":"Qwen3-Embedding-8B","context_length":32768,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":"Qwen/Qwen3-Embedding-8B","open_weights":true,"knowledge_cutoff":null,"reasoning":null,"description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-7},"list_pricing":{"input_cost_per_token":1.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/bge-multilingual-gemma2","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"bge-multilingual-gemma2","context_length":8000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.206480334918941e-7},"list_pricing":{"input_cost_per_token":1.206480334918941e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/qwen3-embedding-8b","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"qwen3-embedding-8b","context_length":32000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":"Qwen/Qwen3-Embedding-8B","open_weights":true,"knowledge_cutoff":null,"reasoning":null,"description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.7420007611794115e-7},"list_pricing":{"input_cost_per_token":2.7420007611794115e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/green-embedding","object":"model","created":1791649789,"owned_by":"greenpt","model_name":"green-embedding","context_length":32000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.193600608943529e-7},"list_pricing":{"input_cost_per_token":2.193600608943529e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/green-embeddings","object":"model","created":1791649789,"owned_by":"greenpt","model_name":"green-embeddings","context_length":32000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.193600608943529e-7},"list_pricing":{"input_cost_per_token":2.193600608943529e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"jina/jina-code-embeddings-0.5b","object":"model","created":1790874047,"owned_by":"jina","model_name":"jina-code-embeddings-0.5b","context_length":32768,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"jina-code-embeddings-0.5b is a 494 million parameter code embedding model designed for retrieving code from natural language queries, technical Q&A, and identifying similar code across languages. Built on Qwen2.5-Coder-0.5B backbone, it generates embeddings via last-token pooling and addresses the fundamental limitation of traditional code embedding models that rely on scarce aligned data like comments and docstrings. The model leverages abundant unaligned code and documentation used in LLM training, achieving state-of-the-art performance despite its compact size. It supports five task categories with specific instruction prefixes: NL2Code, TechQA, Code2Code, Code2NL, and Code2Completion. The model implements Matryoshka representation learning for truncatable embeddings, allowing flexible precision-resource trade-offs.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8},"list_pricing":{"input_cost_per_token":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"jina/jina-code-embeddings-1.5b","object":"model","created":1790874047,"owned_by":"jina","model_name":"jina-code-embeddings-1.5b","context_length":32768,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"jina-code-embeddings-1.5b is a 1.54 billion parameter model representing a significant advancement in code retrieval capabilities. Built on Qwen2.5-Coder-1.5B backbone with last-token pooling, it moves beyond traditional training on limited aligned data to leverage vast unaligned code and documentation corpora. The model implements comprehensive task-specific instructions across five categories: NL2Code, TechQA, Code2Code, Code2NL, and Code2Completion, each with distinct prefixes for queries and documents. Supports Matryoshka representation learning for flexible embedding truncation. Despite larger size, maintains practical deployment characteristics while achieving benchmark performance competitive with substantially larger alternatives.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8},"list_pricing":{"input_cost_per_token":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"jina/jina-embeddings-v2-base-code","object":"model","created":1790874047,"owned_by":"jina","model_name":"jina-embeddings-v2-base-code","context_length":8192,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Jina Embeddings v2 Base Code tackles a critical challenge in modern software development: efficiently navigating and understanding large codebases. For development teams struggling with code discovery and documentation, this model transforms how developers interact with code by enabling natural language search across 30 programming languages. Unlike traditional code search tools that rely on exact pattern matching, this model understands the semantic meaning behind code, allowing developers to find relevant code snippets using plain English descriptions. This capability is particularly valuable for teams maintaining large legacy codebases, developers onboarding to new projects, or organizations looking to improve code reuse and documentation practices.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8},"list_pricing":{"input_cost_per_token":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"jina/jina-embeddings-v2-base-de","object":"model","created":1790874047,"owned_by":"jina","model_name":"jina-embeddings-v2-base-de","context_length":8192,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Jina Embeddings v2 Base German addresses a critical challenge in international business: bridging the language gap between German and English markets. For German companies expanding into English-speaking territories, where a third of businesses generate over 20% of their global sales, accurate bilingual understanding is essential. This model transforms how organizations handle cross-language content by enabling seamless text understanding and retrieval in both German and English, making it invaluable for companies implementing international documentation systems, customer support platforms, or content management solutions. Unlike traditional translation-based approaches, this model directly maps equivalent meanings in both languages to the same embedding space, enabling more accurate and efficient bilingual operations.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8},"list_pricing":{"input_cost_per_token":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"jina/jina-embeddings-v2-base-en","object":"model","created":1790874047,"owned_by":"jina","model_name":"jina-embeddings-v2-base-en","context_length":8192,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Jina Embeddings v2 Base English is a groundbreaking open-source text embedding model that solves the critical challenge of processing long documents while maintaining high accuracy. Organizations struggling with analyzing extensive legal documents, research papers, or financial reports will find this model particularly valuable. It stands out by handling documents up to 8,192 tokens in length—16 times longer than traditional models—while matching the performance of OpenAI's proprietary solutions. With a compact size of 0.27GB and efficient resource usage, it offers an accessible solution for teams seeking to implement advanced document analysis without excessive computational overhead.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8},"list_pricing":{"input_cost_per_token":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"jina/jina-embeddings-v2-base-es","object":"model","created":1790874047,"owned_by":"jina","model_name":"jina-embeddings-v2-base-es","context_length":8192,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Jina Embeddings v2 Base Spanish is a groundbreaking bilingual text embedding model that addresses the critical challenge of cross-lingual information retrieval and analysis between Spanish and English content. Unlike traditional multilingual models that often show bias towards specific languages, this model delivers truly balanced performance across both Spanish and English, making it indispensable for organizations operating in Spanish-speaking markets or handling bilingual content. The model's most remarkable feature is its ability to generate geometrically aligned embeddings - when texts in Spanish and English express the same meaning, their vector representations naturally cluster together in the embedding space, enabling seamless cross-language search and analysis.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8},"list_pricing":{"input_cost_per_token":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"jina/jina-embeddings-v2-base-zh","object":"model","created":1790874047,"owned_by":"jina","model_name":"jina-embeddings-v2-base-zh","context_length":8192,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Jina Embeddings v2 Base Chinese breaks new ground as the first open-source model to seamlessly handle both Chinese and English text with an unprecedented 8,192 token context length. This bilingual powerhouse addresses a critical challenge in global business: the need for accurate, long-form document processing across Chinese and English content. Unlike traditional models that struggle with cross-lingual understanding or require separate models for each language, this model maps equivalent meanings in both languages to the same embedding space, making it invaluable for organizations expanding globally or managing multilingual content.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8},"list_pricing":{"input_cost_per_token":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"jina/jina-embeddings-v3","object":"model","created":1790874047,"owned_by":"jina","model_name":"jina-embeddings-v3","context_length":8192,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Jina Embeddings v3 is a groundbreaking multilingual text embedding model that transforms how organizations handle text understanding and retrieval across languages. At its core, it solves the critical challenge of maintaining high performance across multiple languages and tasks while keeping computational requirements manageable. The model particularly shines in production environments where efficiency matters - it achieves state-of-the-art performance with just 570M parameters, making it accessible for teams that can't afford the computational overhead of larger models. Organizations needing to build scalable, multilingual search systems or analyze content across language barriers will find this model especially valuable.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8},"list_pricing":{"input_cost_per_token":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"jina/jina-embeddings-v5-text-nano","object":"model","created":1790874047,"owned_by":"jina","model_name":"jina-embeddings-v5-text-nano","context_length":8192,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Jina Embeddings v5 Text Nano is a lightweight multilingual text embedding model with 239M parameters built on the EuroBERT-210M backbone. It supports 8K context length and produces 768-dimensional embeddings with Matryoshka representation learning (down to 32 dimensions). It uses last-token pooling and supports retrieval, text-matching, clustering, and classification tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-8},"list_pricing":{"input_cost_per_token":2e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"jina/jina-embeddings-v5-text-small","object":"model","created":1790874047,"owned_by":"jina","model_name":"jina-embeddings-v5-text-small","context_length":32768,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Jina Embeddings v5 Text Small is a multilingual text embedding model with 677M parameters built on the Qwen3-0.6B-Base backbone. It supports 32K context length and produces 1024-dimensional embeddings with Matryoshka representation learning (down to 32 dimensions). It uses last-token pooling and supports retrieval, text-matching, clustering, and classification tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8},"list_pricing":{"input_cost_per_token":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"databricks/databricks-qwen3-embedding-0-6b","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-qwen3-embedding-0-6b","context_length":32768,"max_input_tokens":32768,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Qwen3 Embedding is a multilingual text embedding model that can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":0.0,"input_dbu_cost_per_token":2.86e-7,"output_dbu_cost_per_token":0.0,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":2e-8},"list_pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":0.0,"input_dbu_cost_per_token":2.86e-7,"output_dbu_cost_per_token":0.0,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":2e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/amazon.titan-embed-g1-text-02","object":"model","created":1782850127,"owned_by":"amazon","model_name":"amazon.titan-embed-g1-text-02","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"google/gemini-embedding-2","object":"model","created":1779290135,"owned_by":"google","model_name":"gemini-embedding-2","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG).","source":"https://cloud.google.com/vertex-ai/generative-ai/pricing","capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["embeddings","text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":true,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":0.0,"input_cost_per_audio_token":6.5e-6,"input_cost_per_image_token":4.5e-7,"input_cost_per_video_token":0.000012},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":0.0,"input_cost_per_audio_token":6.5e-6,"input_cost_per_image_token":4.5e-7,"input_cost_per_video_token":0.000012},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"google/gemini-embedding-2-preview","object":"model","created":1779290135,"owned_by":"google","model_name":"gemini-embedding-2-preview","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG).","source":"https://cloud.google.com/vertex-ai/generative-ai/pricing","capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["embeddings","text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":true,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":0.0,"input_cost_per_audio_token":6.5e-6,"input_cost_per_image_token":4.5e-7,"input_cost_per_video_token":0.000012},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":0.0,"input_cost_per_audio_token":6.5e-6,"input_cost_per_image_token":4.5e-7,"input_cost_per_video_token":0.000012},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"cohere/embed-english-light-v3.0","object":"model","created":1777907505,"owned_by":"cohere","model_name":"embed-english-light-v3.0","context_length":1024,"max_input_tokens":1024,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"cohere/embed-english-v3.0","object":"model","created":1777907505,"owned_by":"cohere","model_name":"embed-english-v3.0","context_length":1024,"max_input_tokens":1024,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":true,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_image":0.0001,"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_image":0.0001,"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"cohere/embed-multilingual-light-v3.0","object":"model","created":1777907505,"owned_by":"cohere","model_name":"embed-multilingual-light-v3.0","context_length":1024,"max_input_tokens":1024,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":true,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0001,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":0.0001,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"cohere/embed-multilingual-v3.0","object":"model","created":1777907505,"owned_by":"cohere","model_name":"embed-multilingual-v3.0","context_length":1024,"max_input_tokens":1024,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":true,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"cohere/embed-v4.0","object":"model","created":1777907505,"owned_by":"cohere","model_name":"embed-v4.0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":true,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"mistral/codestral-embed@eu","object":"model","created":1777907505,"owned_by":"mistral","model_name":"codestral-embed","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"cache_read_input_token_cost_batches":8.25e-9},"list_pricing":{"input_cost_per_token":1.65e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"cache_read_input_token_cost_batches":8.25e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/codestral-embed","object":"model","created":1777907505,"owned_by":"mistral","model_name":"codestral-embed","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"cache_read_input_token_cost_batches":7.5e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"cache_read_input_token_cost_batches":7.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-embed@eu","object":"model","created":1777907505,"owned_by":"mistral","model_name":"mistral-embed","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"list_pricing":{"input_cost_per_token":1.1e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-embed","object":"model","created":1777907505,"owned_by":"mistral","model_name":"mistral-embed","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"cache_read_input_token_cost_batches":5e-9},"list_pricing":{"input_cost_per_token":1e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"cache_read_input_token_cost_batches":5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/amazon.nova-2-multimodal-embeddings-v1:0","object":"model","created":1777537865,"owned_by":"amazon","model_name":"amazon.nova-2-multimodal-embeddings-v1:0","context_length":8172,"max_input_tokens":8172,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":"https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/model-catalog/serverless/amazon.nova-2-multimodal-embeddings-v1:0","capabilities":{"input_modalities":["text","audio","video"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":true,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_image":0.00006,"input_cost_per_token":1.35e-7,"output_cost_per_token":0.0,"input_cost_per_audio_per_second":0.00014,"input_cost_per_video_per_second":0.0007},"list_pricing":{"input_cost_per_image":0.00006,"input_cost_per_token":1.35e-7,"output_cost_per_token":0.0,"input_cost_per_audio_per_second":0.00014,"input_cost_per_video_per_second":0.0007},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/cohere.embed-english-v3","object":"model","created":1777537865,"owned_by":"amazon","model_name":"cohere.embed-english-v3","context_length":512,"max_input_tokens":512,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":true,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/cohere.embed-english-v3@us","object":"model","created":1777537865,"owned_by":"amazon","model_name":"cohere.embed-english-v3","context_length":512,"max_input_tokens":512,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":true,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/cohere.embed-multilingual-v3","object":"model","created":1777537865,"owned_by":"amazon","model_name":"cohere.embed-multilingual-v3","context_length":512,"max_input_tokens":512,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":true,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/cohere.embed-multilingual-v3@us","object":"model","created":1777537865,"owned_by":"amazon","model_name":"cohere.embed-multilingual-v3","context_length":512,"max_input_tokens":512,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":true,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/cohere.embed-v4:0","object":"model","created":1777537865,"owned_by":"amazon","model_name":"cohere.embed-v4:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":true,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/cohere.embed-v4:0@us","object":"model","created":1777537865,"owned_by":"amazon","model_name":"cohere.embed-v4:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":true,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-bge-large-en","object":"model","created":1777537865,"owned_by":"databricks","model_name":"databricks-bge-large-en","context_length":512,"max_input_tokens":512,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"BAAI general embedding (BGE) can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. And it also can be used in vector databases for LLMs.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":0.0,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":0.0,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gte-large-en","object":"model","created":1777537865,"owned_by":"databricks","model_name":"databricks-gte-large-en","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"General text embeddings (GTE) can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. And it also can be used in vector databases for LLMs.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":0.0,"input_dbu_cost_per_token":1.857e-6,"output_dbu_cost_per_token":0.0,"cache_read_input_token_cost":1.3e-7,"cache_creation_input_token_cost":1.3e-7},"list_pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":0.0,"input_dbu_cost_per_token":1.857e-6,"output_dbu_cost_per_token":0.0,"cache_read_input_token_cost":1.3e-7,"cache_creation_input_token_cost":1.3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"mistral/mistral-embed-2312@eu","object":"model","created":1761944622,"owned_by":"mistral","model_name":"mistral-embed-2312","context_length":8192,"max_input_tokens":8192,"max_output_tokens":6553,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Mistral Embed is a specialized embedding model for text data, optimized for semantic search and RAG applications.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":0.0,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":0.0,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-embed-2312","object":"model","created":1761944622,"owned_by":"mistral","model_name":"mistral-embed-2312","context_length":8192,"max_input_tokens":8192,"max_output_tokens":6553,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Mistral Embed is a specialized embedding model for text data, optimized for semantic search and RAG applications.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"cache_read_input_token_cost_batches":5e-9},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"cache_read_input_token_cost_batches":5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"google/gemini-embedding-001","object":"model","created":1761943410,"owned_by":"google","model_name":"gemini-embedding-001","context_length":20000,"max_input_tokens":2048,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding.","source":"https://ai.google.dev/gemini-api/docs/embeddings#model-versions","capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-embedding-001","object":"model","created":1761943410,"owned_by":"vertex","model_name":"gemini-embedding-001","context_length":20000,"max_input_tokens":2048,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":0.0,"input_cost_per_audio_token":0.0,"input_cost_per_image_token":0.0},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":0.0,"input_cost_per_audio_token":0.0,"input_cost_per_image_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/text-embedding-ada-002","object":"model","created":1761865798,"owned_by":"openai","model_name":"text-embedding-ada-002","context_length":8192,"max_input_tokens":8191,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"text-embedding-ada-002 is OpenAI's legacy text embedding model.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"mistral/codestral-embed-2505@eu","object":"model","created":1761864460,"owned_by":"mistral","model_name":"codestral-embed-2505","context_length":8192,"max_input_tokens":8192,"max_output_tokens":6553,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":0.0,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"cache_read_input_token_cost_batches":8.25e-9},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":0.0,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"cache_read_input_token_cost_batches":8.25e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/codestral-embed-2505","object":"model","created":1761864460,"owned_by":"mistral","model_name":"codestral-embed-2505","context_length":8192,"max_input_tokens":8192,"max_output_tokens":6553,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":0.0,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"cache_read_input_token_cost_batches":7.5e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":0.0,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"cache_read_input_token_cost_batches":7.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/text-embedding-3-large","object":"model","created":1761862866,"owned_by":"openai","model_name":"text-embedding-3-large","context_length":8192,"max_input_tokens":8191,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":0.0,"input_cost_per_token_batches":6.5e-8,"output_cost_per_token_batches":0.0},"list_pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":0.0,"input_cost_per_token_batches":6.5e-8,"output_cost_per_token_batches":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/text-embedding-3-small","object":"model","created":1761857455,"owned_by":"openai","model_name":"text-embedding-3-small","context_length":8192,"max_input_tokens":8191,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":"text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":0.0,"input_cost_per_token_batches":1e-8,"output_cost_per_token_batches":0.0},"list_pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":0.0,"input_cost_per_token_batches":1e-8,"output_cost_per_token_batches":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"nebius/Qwen/Qwen3-Embedding-8B","object":"model","created":1761680622,"owned_by":"nebius","model_name":"Qwen/Qwen3-Embedding-8B","context_length":40960,"max_input_tokens":40960,"max_output_tokens":32000,"quantization":"bf16","retirement_date":null,"hugging_face_id":"Qwen/Qwen3-Embedding-8B","open_weights":true,"knowledge_cutoff":null,"reasoning":null,"description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["embeddings","text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-8,"output_cost_per_token":0.0,"cache_read_input_token_cost":1e-8},"list_pricing":{"input_cost_per_token":1e-8,"output_cost_per_token":0.0,"cache_read_input_token_cost":1e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/qwen3-embedding-8b","object":"model","created":1755006551,"owned_by":"scaleway","model_name":"qwen3-embedding-8b","context_length":null,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":"Qwen/Qwen3-Embedding-8B","open_weights":true,"knowledge_cutoff":null,"reasoning":null,"description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0968003044717645e-7},"list_pricing":{"input_cost_per_token":1.0968003044717645e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/bge-multilingual-gemma2","object":"model","created":1730385501,"owned_by":"scaleway","model_name":"bge-multilingual-gemma2","context_length":null,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"hugging_face_id":null,"open_weights":null,"knowledge_cutoff":null,"reasoning":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0968003044717645e-7},"list_pricing":{"input_cost_per_token":1.0968003044717645e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}]}